We are seeking a skilled AI Engineer with hands-on experience in building intelligent, production-grade applications powered by Large Language Models (LLMs). The role focuses on designing scalable RAG-based systems, agentic workflows, and real-time AI applications using modern orchestration frameworks such as LangChain and LangGraph.
The ideal candidate will have strong expertise in Python, vector search, embeddings, and distributed AI system design, along with experience in building autonomous AI agents and inter-agent communication using A2A (Agent-to-Agent) protocols.
Experience: 1–2 Years
Location: Bangalore
Employment Type: Full-Time
Key Responsibilities- Design and build end-to-end RAG (Retrieval Augmented Generation) pipelines for real-time AI applications.
- Develop and manage AI agents and multi-agent workflows using LangGraph and LangChain.
- Implement Agent-to-Agent (A2A) communication protocols for collaborative and autonomous AI systems.
- Strong understanding of the MCP Protocol.
- Build intelligent applications such as chatbots, semantic search systems, recommendation engines, and workflow automation tools.
- Design and optimize embedding pipelines for text, documents, and structured data.
- Implement scalable semantic and similarity search using vector databases.
- Integrate and manage vector databases such as Pinecone, Weaviate, Milvus, FAISS, Chroma, and OpenSearch Vector Engine.
- Work with LLM providers including OpenAI, Azure OpenAI, Anthropic, Google Gemini, Meta LLaMA, and Mistral.
- Fine-tune prompt strategies, system prompts, and agent behaviors for optimal performance.
- Build robust backend services and APIs using Python (FastAPI preferred).
- Implement ranking, filtering, and metadata-based retrieval mechanisms.
- Optimize LLM performance for latency, cost, and scalability (caching, batching, streaming).
- Ensure AI safety, hallucination mitigation, and response validation.
- Collaborate with product, frontend, and data teams to deliver end-to-end AI solutions.
- Deploy and manage AI workloads on cloud platforms (AWS, Azure, GCP).
- Maintain CI/CD pipelines and production-grade AI infrastructure.
Required Skills & QualificationsCore AI & LLM Expertise- Strong understanding of:
- Embeddings and vector representations
- Similarity search (cosine similarity, dot product, ANN indexing)
- Hands-on experience with:
- LangChain and LangGraph (mandatory)
- RAG architectures and pipelines
- Agentic AI systems and orchestration
- Experience implementing multi-agent systems and A2A protocols
- Proficiency in prompt engineering and LLM orchestration
Programming & Backend- Strong proficiency in Python (mandatory)
- Experience building APIs using FastAPI / Flask
- Solid understanding of REST APIs, async processing, and microservices architecture
Data & Storage- Experience with relational and NoSQL databases (PostgreSQL, MySQL, MongoDB)
- Familiarity with vector databases (at least one required)
- Knowledge of data preprocessing, chunking, and tokenization strategies
- Experience with object storage (AWS S3, Azure Blob, GCP Storage)
Cloud & DevOps (Good to Have)- Docker and Kubernetes
- CI/CD pipelines (GitHub Actions, Jenkins, GitLab)
- Monitoring tools (Prometheus, Grafana, OpenTelemetry)
Good to Have (Preferred Skills)- Experience with advanced agentic AI frameworks and autonomous workflows
- Knowledge of tool calling / function calling in LLMs
- Exposure to multimodal AI (speech-to-text, vision models)
- Experience with fine-tuning, LoRA, or model adaptation techniques
- Understanding of AI security, governance, and data privacy
- Experience building distributed AI systems with multiple interacting agents
Use Cases You Will Work On- AI-powered customer support chatbots
- Semantic document and enterprise search systems
- Knowledge-base Q&A platforms
- Recommendation engines
- Automated ticket triaging systems
- Developer and operations AI assistants
- Multi-agent intelligent workflow automation systems
